This role involves exploring and developing novel reinforcement learning (RL) algorithms to address challenges in game contexts, training RL models on innovative and practical tasks, and proactively collaborating with team members to achieve research goals. Candidates must have hands-on experience implementing RL algorithms in Python using frameworks like PyTorch, be able to tune and optimize RL models, and be proficient in English.

Must Have

• Hands-on experience implementing RL algorithms in Python, using popular frameworks such as PyTorch.
• Ability to tune and optimize reinforcement learning models.
• Proficiency in English.

Good to Have

• Familiarity with cooperative multi-agent reinforcement learning, ad-hoc teamwork, or human-AI cooperation technologies.
• Experience publishing papers in top conferences (e.g., NeurIPS, ICML, ICLR).
• Bilingual proficiency in Chinese or Japanese.

Perks & Benefits

• Negotiable annual salary (with raises/bonuses)
• Fixed overtime pay included (35 hours/month for general employees, 10 hours/month for managers)
• Working hours: 09:30 ~ 18:30 with a 60-minute break
• Flexible working hours available
• Complete two-day weekend system (Saturdays, Sundays, public holidays)
• Paid leave (prorated first year, up to 22 days based on years of service)
• Year-end and New Year holidays (Dec 30 - Jan 3)
• Paid sick leave: 12 days/year (separate from paid leave)
• Health insurance
• Employment insurance
• Workers' accident compensation insurance
• Employees' pension insurance
• Group Term Life Insurance (GTL)
• Comprehensive Business Accident Relief Insurance (GPA)
• Group Long Term Disability Income Compensation Insurance (GLTD)
• Overseas travel insurance
• Commuting allowance (up to 50,000 JPY/month)
• Communication allowance (up to 10,000 JPY/month)
• Self-development allowance (up to 20,000 JPY/month)
• Meal subsidy 1,800 JPY/day for working on weekdays
• Regular health check-up allowance (up to 75,000 JPY/year, once a year)
• Free drink corner
• Gift cards (20,000 JPY/time, twice a year for Obon and New Year)
• Employee Assistance Program (EAP)
• Condolence and congratulatory payments
• Long service award/leave

Business Unit

LIGHTSPEED STUDIOS continues to pursue game development as a fusion of art and science, utilizing highly narrative stories, immersive gameplay, and cutting-edge technology. Our mission is to deliver next-generation gaming experiences to players worldwide, across all devices.

About the Hiring Team

Lightspeed Tech Center is the R&D department of Lightspeed Studios, which has developed various high-quality games, including PUBG Mobile. The Tech Center drives technological research and innovation, providing technical support throughout the lifecycle of game titles, including engine, audio, QA, AI, next-generation technology, and technical partnerships.

What the Role Entails

Job Responsibilities:

1. Explore and develop novel reinforcement learning (RL) algorithms to address challenges in game contexts.

2. Train RL models on innovative and practical tasks.

3. Collaborate proactively with team members to achieve research goals.

Who We Look For

Requirements:

1. Hands-on experience implementing RL algorithms in Python, using popular frameworks such as PyTorch.

2. Must be able to tune and optimize reinforcement learning models.

3. Must be proficient in English.

4. Preferred: Familiarity with cooperative multi-agent reinforcement learning, ad-hoc teamwork, or human-AI cooperation technologies.

5. Preferred: Experience publishing papers in top conferences (e.g., NeurIPS, ICML, ICLR).

6. Preferred: Bilingual proficiency in Chinese or Japanese.

Why Join Us?

Salary:

Annual salary: negotiable (with raises/bonuses)

• Consideration will be given to experience and skills, and preferential treatment will be given according to company regulations.
• For general employees, 35 hours of fixed overtime pay per month is included.
• For managers, 10 hours of fixed overtime pay is included.

Working Hours/Holidays:

Working hours: 09:30 ~ 18:30, Break time: 60 minutes

Flexible working hours available

Complete two-day weekend system (Saturdays, Sundays, public holidays)

Paid leave: For the first year of employment, prorated based on the joining month. Up to 22 days based on years of service.

Year-end and New Year holidays (Dec 30 - Jan 3)

Paid sick leave: 12 days/year (granted separately from paid leave)

Benefits:

Health insurance, Employment insurance, Workers' accident compensation insurance, Employees' pension insurance, Group Term Life Insurance (GTL)

Comprehensive Business Accident Relief Insurance (GPA), Group Long Term Disability Income Compensation Insurance (GLTD)

Overseas travel insurance

Commuting allowance (up to 50,000 JPY/month), Communication allowance (up to 10,000 JPY/month), Self-development allowance (up to 20,000 JPY/month), Meal subsidy 1,800 JPY/day for working on weekdays, Regular health check-up allowance (up to 75,000 JPY/year, once a year)

Free drink corner, Gift cards (20,000 JPY/time, twice a year for Obon and New Year)

Employee Assistance Program (EAP), Condolence and congratulatory payments, Long service award/leave

The policies stated in this job advertisement (including but not limited to salary, benefits, working conditions) may be adjusted according to the company's real-time policies.

Equal Employment Opportunity at Tencent

As an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.